Add example on fine-tuning for function calling

mlabonne / llm-course

Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.

https://mlabonne.github.io/blog/

Apache License 2.0

38.42k stars 4.07k forks source link

Add example on fine-tuning for function calling #13

Open homanp opened 11 months ago

homanp commented 11 months ago

Hey @mlabonne

Great work on this repo!

Would be amazing if you would want to add an example of fine-tuning for function calling. This would gain a lot of traction due to devs wanting OSS alternatives to GPT.

mlabonne commented 11 months ago

Hi @homanp it's a great idea. I'm writing it down for a future article, thanks! :)

vikram71198 commented 10 months ago

@mlabonne I would heavily suggest SFT-ing this newly released model by Nexusflow, which surpasses GPT-4 according to their evals. There is a discussion thread on the page here, where they suggest that simple instruct tuning (ideally only on the completions) can go pretty far.

If you want, I could work on this when I have time over the next few weeks.

mlabonne commented 10 months ago

@vikram71198 Very interesting, please let me know if you do it!

pranjal376 commented 9 months ago

ohh